~ / directory / perplexity
PE
Generative · Foundation Models · reviewed 2026-04

Perplexity

Conversational web search using multiple LLMs.

Visit www.perplexity.ai
01

What it does

A conversational web search engine powered by multiple LLMs. Provides sourced, cited answers to queries by searching the web and synthesising results in real-time.

02

Security relevance

Perplexity is a shadow AI risk vector — employees using it for research may inadvertently share sensitive query context with external AI services. Unlike traditional search engines, Perplexity processes and reasons about query context, potentially exposing more information than a simple search query would.

03

When to use it

Monitor for shadow AI usage in your organisation. Perplexity itself is a browser-based tool with zero setup — the security concern is governance and awareness rather than technical controls.

04

OWASP coverage

Risks addressed — mapped to both OWASP Top 10 standards. 1 in LLM, 0 in Agentic.

LLM Top 10 · 2025 · 1/10 covered
01
02
03
04
05
06
07
08
09
10
Agentic Top 10 · 2026 · 0/10 covered
01
02
03
04
05
06
07
08
09
10
05

The raw record

What Yuntona stores. Single source of truth — fork it on GitHub.

name: Perplexity
slug: perplexity
type: Generative
category: Foundation Models
url: https://www.perplexity.ai

reviewed:   2026-04
added:      2026-04
updated:    2026-04

risks:
  llm:  [LLM06]
  asi:  []

complexity:    Plug & Play
pricing:       —
audience:      All
lifecycle:     []

tags: [LLM, Search, Shadow AI]